FreeTuner: Any Subject in Any Style with Training-free Diffusion

TL;DR

FreeTuner is a training-free diffusion-based method enabling compositional personalization of images by combining user-defined subjects and styles, overcoming previous limitations in concept disentanglement and data requirements.

Contribution

It introduces a novel, training-free approach that disentangles subject and style concepts within diffusion models for flexible compositional image personalization.

Findings

Effective subject-style compositional generation demonstrated

Outperforms existing personalization methods in quality and flexibility

Works with minimal or no additional training data

Abstract

With the advance of diffusion models, various personalized image generation methods have been proposed. However, almost all existing work only focuses on either subject-driven or style-driven personalization. Meanwhile, state-of-the-art methods face several challenges in realizing compositional personalization, i.e., composing different subject and style concepts, such as concept disentanglement, unified reconstruction paradigm, and insufficient training data. To address these issues, we introduce FreeTuner, a flexible and training-free method for compositional personalization that can generate any user-provided subject in any user-provided style (see Figure 1). Our approach employs a disentanglement strategy that separates the generation process into two stages to effectively mitigate concept entanglement. FreeTuner leverages the intermediate features within the diffusion model for subject concept representation and introduces style guidance to align the synthesized images with the style concept, ensuring the preservation of both the subject's structure and the style's aesthetic features. Extensive experiments have demonstrated the generation ability of FreeTuner across various personalization settings.